Tesi sul tema "Unmanned ground vehicles"

Unmanned ground vehicles (UGVs) are increasingly being used for civilian and military applications. Passive sensing, such as visible cameras, are being used for navigation and object detection. An additional object of interest in many environments is text. Text information can supplement the autonomy of unmanned ground vehicles. Text most often appears in the environment in the form of road signs and storefront signs. Road hazard information, unmapped route detours and traffic information are available to human drivers through road signs. Premade road maps lack these traffic details, but with text localization the vehicle could fill the information gaps. Leading text localization algorithms achieve ~60% accuracy; however, practical applications are cited to require at least 80% accuracy [49]. The goal of this thesis is to test existing text localization algorithms against challenging scenes, identify the best candidate and optimize it for scenes a UGV would encounter. Promising text localization methods were tested against a custom dataset created to best represent scenes a UGV would encounter. The dataset includes road signs and storefront signs against complex background. The methods tested were adaptive thresholding, the stroke filter and the stroke width transform. A temporal tracking proof of concept was also tested. It tracked text through a series of frames in order to reduce false positives. Best results were obtained using the stroke width transform with temporal tracking which achieved an accuracy of 79%. That level of performance approaches requirements for use in practical applications. Without temporal tracking the stroke width transform yielded an accuracy of 46%. The runtime was 8.9 seconds per image, which is 44.5 times slower than necessary for real-time object tracking. Converting the MATLAB code to C++ and running the text localization on a GPU could provide the necessary speedup
Master of Science

Unmanned ground vehicles are increasingly employing a combination of active sensors such as LIDAR with passive sensors like cameras to perform at all levels of perception, which includes detection, recognition and classification. Typical cameras measure the intensity of light at a variety of different wavelengths to classify objects in different areas of an image. A polarimetric camera not only measures intensity of light, but can also determine its state of polarization. The polarization of light is the angle the electric field of the wave of light takes as it travels. A polarimetric camera can identify the state of polarization of the light, which can be used to segment highly polarizing areas in a natural environment, such the surface of water. The polarimetric camera designed and built for this thesis was created with low cost in mind, as commercial polarimetric cameras are very expensive. It uses multiple beam splitters to split incoming light into four machine vision cameras. In front of each machine vision camera is a linear polarizing filter that is set to a specific orientation. Using the data from each camera, the Stokes vector can be calculated on a pixel by pixel basis to determine what areas of the image are more polarized. Test images of various scenes that included running water, standing water, mud, and vehicles showed promise in using polarization data to highlight and identify areas of interest. This data could be used by a UGV to make more informed decisions in an autonomous navigation mode.
Master of Science

Thesis (M.S.) -- University of Maryland, College Park, 2005.
Thesis research directed by: Dept. of Electrical and Computer Engineering. Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.

Mobile robots are commonly used to achieve tasks involving tracking a desired trajectory and following a predefined path in different types of terrains that have different surface characteristics. A mobile robot can perform the same navigation task task over different surfaces if the tracking performance and accuracy are not essential. However, if the tracking performance is the main objective, due to changing the characteristics of wheel-ground interaction, a single set of controller parameters or an equation of motion might be easily failing to guarantee a desired performance and accuracy. The interaction occurring between the wheels and ground can be integrated into the system model so that the performance of the mobile robot can be enhanced on various surfaces. This modeling approach related to wheel-ground interaction can also be incorporated into the motion controller. In this thesis study, modeling studies for a two wheeled differential drive mobile robot and a steerable four-wheeled robot vehicle are carried out. A strategy to achieve better tracking performance for a differential drive mobile robot is developed by introducing a procedure including the effects of external wheel forces
i.e, traction, rolling and lateral. A new methodology to represent the effects of lateral wheel force is proposed. An estimation procedure to estimate the parameters of external wheel forces is also introduced. Moreover, a modeling study that is related to show the effects of surface inclination on tracking performance is performed and the system model of the differential drive mobile robot is updated accordingly. In order to accomplish better trajectory tracking performance and accuracy for a steerable four-wheeled mobile robot, a modeling work that includes a desired trajectory generator and trajectory tracking controller is implemented. The slippage is defined via the slip velocities of steerable front and motorized rear wheels of the mobile robot. These slip velocities are obtained by using the proposed slippage estimation procedure. The estimated slippage information is then comprised into the system model so as to increase the performance and accuracy of the trajectory tracking tasks. All the modeling studies proposed in this study are tested by using simulations and verified on experimental platforms.

Thesis (S.M. and E.A.A.)--Massachusetts Institute of Technology, Dept. of Aeronautics and Astronautics, 2004.
"June 2004."
Includes bibliographical references (p. 95).
This thesis summarizes the results of the design of avionics systems intended for use onboard unmanned air and ground vehicles, that are parts of a multi-vehicle system whose primary mission objective is to provide up-close surveillance capability from a large stand-off distance. Different types of cooperative action between air and ground vehicles, that can help to enhance the overall system surveillance capability, are analyzed, including communication relay, simultaneous visual surveillance of ground objects from air and ground vehicles, and visual coverage of ground vehicles from air vehicles. Both hardware and software design as well as practical implementation of the designed avionics systems are discussed, and results of field tests are presented.
by Alexander Omelchenko.
S.M.and E.A.A.

Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Mechanical Engineering, 2005.
"June 2005."
Includes bibliographical references (p. 111-116).
High-speed unmanned ground vehicles have important applications in rough-terrain. In these applications unexpected and dangerous situations can occur that require rapid hazard avoidance maneuvers. At high speeds, there is limited time to perform navigation and hazard avoidance calculations based on detailed vehicle and terrain models. Furthermore, detailed models often do not accurately predict the robot's performance due to model parameter and sensor uncertainty. This thesis presents the development and analysis of a novel method for high speed navigation and hazard avoidance. The method is based on the two dimensional "trajectory space," which is a compact model-based representation of a robot's dynamic performance limits on natural terrain. This method allows a vehicle to perform dynamically feasible hazard avoidance maneuvers in a computationally efficient manner. This thesis also presents a novel method for trajectory replanning, based on a "curvature matching" technique. This method quickly generates a path connects the end of the path generated by a hazard avoidance maneuver to the nominal desired path. Simulation and experimental results with a small gasoline-powered high-speed unmanned ground vehicle verify the effectiveness of these algorithms. The experimental results demonstrate the ability of the algorithm to account for multiple hazards, varying terrain inclination, and terrain roughness. The experimental vehicle attained speeds of 8 m/s (18 mph) on flat and sloped terrain and 7 m/s (16 mph) on rough terrain.
by Matthew J. Spenko.
Ph.D.

The purpose of this project is to implement obstacle avoidance algorithms to drive the articulated vehicle autonomously in an unknown environment, which is simulated by AgX Dynamics™ simulation software and controlled by Matlab® programming software. Three driving modes are developed for driving the vehicle (Manual, Semi-autonomous and Autonomous) in this project. Path tracking algorithms and obstacle avoidance algorithms are implemented to navigate the vehicle. A GUI was built and used for the manual driving mode in this project. The semi-autonomous mode checked different cases: change lanes, U-turn, following a line, following a path and figure 8 course. The autonomous mode is implemented to drive the articulated vehicle in an unknown environment with moving to a pose path tracking algorithm and VFH+ obstacle avoidance algorithm. Thus, the simulation model and VFH+ obstacle avoidance algorithm seems to be working fine and still can be improved for the autonomous vehicle. The result of this project showed a good performance of the simulation model. Moreover, this simulation software helps to minimize the cost of the articulated vehicle since all tests are in the simulation rather than in the reality.

The fast technology development for military unmanned ground vehicles (UGVs) has led to a considerable demand to explore the soldier’s role in an interactive UGV system. This thesis explores how to design interactive systems for UGVs for infantry soldiers in the Swedish Armed Force. This was done through a user-centered design approach in three steps; (1) identifying the design drivers of the targeted military context through qualitative observations and user interviews, (2) using the design drivers to investigate concepts for controlling the UGV, and (3) create and evaluate a prototype of an interactive UGV system design. Results from interviews indicated that design drivers depend on the physical and psychological context of the intended soldiers. In addition, exploring the different concepts showed that early conceptual designs helped the user express their needs of a non-existing system. Furthermore, the results indicate that an interactive UGV system does not necessarily need to be at the highest level of autonomy in order to be useful for the soldiers on the field. The final prototype of an interactive UGV system was evaluated using a demonstration video, a Technology Acceptance Model (TAM), and semi-structured user interviews. Results from this evaluation suggested that the soldiers see the potential usefulness of an interactive UGV system but are not entirely convinced. In conclusion, this thesis argues that in order to design an interactive UGV system, the most critical aspect is the soldiers’ acceptance of the new system. Moreover, for soldiers to accept the concept of military UGVs, it is necessary to understand the context of use and the needs of the soldiers. This is done by involving the soldiers already in the conceptual design process and then throughout the development phases.

Many applications for unmanned vehicles involve autonomous interaction between two or more craft, and therefore, relative navigation is a key issue to explore. Several high fidelity hardware simulations exist to produce accurate dynamics. However, these simulations are restricted by size, weight, and power needed to operate them. The use of a small Unmanned Ground Vehicle (UGV) for the relative navigation problem is investigated. The UGV has the ability to traverse large ranges over uneven terrain and into varying lighting conditions which has interesting applications to relative navigation. The basic problem of a vehicle following another is researched and a possible solution explored. Statistical pressure snakes are used to gather relative position data at a specified frequency. A cubic spline is then fit to the relative position data using a least squares algorithm. The spline represents the path on which the lead vehicle has already traversed. Controlling the UGV onto this relative path using a sliding mode control, allows the follow vehicle to avoid the same stationary obstacles the lead vehicle avoided without any other sensor information. The algorithm is run on the UGV hardware with good results. It was able to follow the lead vehicle around a curved course with only centimeter-level position errors. This sets up a firm foundation on which to build a more versatile relative motion platform.
Master of Science

Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2007.
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Includes bibliographical references (p. 99-101).
Automated ground maintenance is a necessity for multi-UAV systems. Without such automation, these systems will become more of a burden than a benefit as human operators struggle to contend with maintenance operations for large numbers of vehicles. By creating autonomous UAV systems that can take care of themselves, human operators will be free to concentrate on higher level tasks such as using the information gathered by the system to direct future mission activities. This thesis describes the design, testing, construction, and usage of the first fully autonomous recharge system for small, battery-powered UAVs. This system was used to perform the first fully-autonomous quadrotor UAV long-term flight tests and to conduct multi-UAV mission management research. In addition, this thesis describes, to the best of our knowledge, the first landing and recharge of a UAV on a mobile recharge platform.
by Daniel R. Dale.
M.Eng.

New challenges and opportunities arise as a result of an increasing demand of connecting devices in the context of the Internet of Things. Synergy eects can be achieved by connecting local devices through both wireless local networks and global infrastructures. These thoughts were applied in a military use case where the challenge was identied to reduce the risk of human lives in combat by letting an Unmanned Ground Vehicle (UGV) take over the highest risks during re control. This thesis covers the design and evaluation of a system that enhances the aiming control performance of a UGV by allocating image processing tasks to an adaptive local wireless distributed computation network. Background research was conducted through a state of the art survey, literature study and through structured interviews. The system was developed both as a simulation model in TrueTime, and a physical proof of concept demonstrator. A hypothesis was developed that involves a categorization of two classes of QoS arguments including sample rate and end-to-end delay. These two classes were used as a basis foran alyzing the control performance of the UGV in terms of accuracy and precision, and for analyzing the individual impact of the technical parameters of the system. Based on the initial hypothesis, the analysis concludes a potential theoretical speed-up in terms of sample rate of approximately 6 times when implementing wireless distributed computing over Wi-Fi compared, to when the processing tasks are completely managed by the UGV. However, the analysis confirms that the resulting control performance of the UGV is a clear trade-off between the dynamic distribution of computation and communication overheads.
Nya utmaningar och möjligheter kan identifieras till följd av en ökande efterfrågan av att koppla ihop enheter i sammanhanget Internet of Things. Synergieffekter kan uppnås genom att koppla ihop lokala enheter både trådlöst och genom global infrastruktur. Dessa tankar applicerades på ett militärt scenario där en utmaning identifierades att reducera risken för mänskliga liv i strid genom att låta en obemannad markfarkost överta de högsta riskerna under eldledning. Detta examensarbete har som mål att utvärdera ett system som förbättrar reglerprestandan hos en obemannad markfarkost genom att allokera bildbehandlingsuppgifter till ett adaptivt trådlöst distribuerat beräkningsnätverk. Forskningen genomfördes genom en state of the art undersökning, litteraturstudie, och strukturerade intervjuer. Systemet utvecklades både i form av en simuleringsmodell i TrueTime, samt som en fysisk konceptvalidering. En hypotes togs fram som innebar en kategorisering av två klasser för quality of service, samplingshastighet och end-to-end fördröjning. Dessa två klasser anvandes som grund för analysen av reglerprestandan i termer av noggranhet och precision, samt för att analyserade inviduella effekterna av de olika tekniska parametrarna i systemet. Baserat på den initiala hypotesen är slutsatsen av analysen att en potentiell teoretisk prestandaökning i termer av samplingshastighet på 6 gånger uppnås vid implementering av ett trådlost distribueringsnätverk av beräkningskraft över Wi-Fi jämfört med när processeringen hanteras enbart av fordonet. Vidare visar även analysen att den resulterande reglerprestandan är en tydlig avvägning mellan den dynamiska distributionen av beräkningsuppgifter och overhead vid kommunikation.

As unmanned air vehicle (UAV) utilization increases in Wilderness Search and Rescue (WiSAR) efforts, onboard sensors yielding more information will be desired. UAVs can assist WiSAR efforts by accelerating the ground search process through returning quality aerial footage of the terrain. Additionally, tracking the progress of a search by populating a digital map with video resolution data increases confidence that a comprehensive search of the region has been made. This thesis presents methods for acquiring video from multiple video sensors and fusing them into a single rendered video stream as a Virtual Gimbal. The panoramic video stream is the first of its kind to be constructed from video transmissions from a small UAV, and the first known video panorama to be used to quickly survey a region within a WiSAR context. The Virtual Gimbal comprises two video transmissions from a three camera array mounted in a downward-looking configuration on a UAV. This video stream has been shown to decrease the amount of time required to thoroughly survey a region by more than 40 percent.

Presented in this thesis is a collision avoidance algorithm designed around an arc path model. The algorithm was designed for use on Virginia Tech robots entered in the 2003 and 2004 Intelligent Ground Vehicle Competition (IGVC) and on our 2004 entry into the DARPA Grand Challenge. The arc path model was used because of the simplicity of the calculations and because it can accurately represent the base kinematics for Ackerman or differentially steered vehicles. Clothoid curves have been used in the past to create smooth paths with continuously varying curvature, but clothoids are computationally intensive. The circular arc algorithm proposed here is designed with simplicity and versatility in mind. It is readily adaptable to ground vehicles of any size and shape. The algorithm is also designed to run with minimal tuning. The algorithm can be used as a stand alone reactive collision avoidance algorithm in simple scenarios, but it can be better optimized for speed and safety when guided by a global path planner. A complete navigation architecture is presented as an example of how obstacle avoidance can be incorporated in the algorithm.
Master of Science

[ES] Para proporcionar un entorno de tráfico vial más seguro y eficiente, los sistemas ITS o Sistemas Inteligentes de Transporte representan como una solución dotada de avances tecnológicos de vanguardia. La integración de elementos de transporte como automóviles junto con elementos de infraestructura como RoadSide Units (RSUs) ubicados a lo largo de la vía de comunicación permiten ofrecer un entorno de red conectado con múltiples servicios, incluida conectividad a Internet. Esta integración se conoce con el término C-ITS o Sistemas Inteligentes de Transporte Cooperativos. La conexión de automóviles con dispositivos de infraestructura permite crear redes vehiculares conectadas (V2X) vehículo a dispositivos, que ofrecen la posibilidad de nuevos despliegues en aplicaciones C-ITS como las relacionadas con la seguridad. Hoy en día, con el uso masivo de teléfonos inteligentes y debido a su flexibilidad y movilidad, existen varios esfuerzos para integrarlos con los automóviles. De hecho, con el soporte adecuado de unidad a bordo (OBU), los teléfonos inteligentes se pueden integrar perfectamente con las redes vehiculares, permitiendo a los conductores usar sus teléfonos inteligentes como dispositivos de bordo a que participan en los servicios C-ITS, con el objeto de mejorar la seguridad al volante entre otros. Tópico este, que hoy día representa un tema relevante de investigación. Un problema a solucionar surge cuando las comunicaciones vehiculares sufren inferencias y bloqueos de la señal debidos al escenario. De hecho, el impacto de la vegetación y los edificios, ya sea en áreas urbanas y rurales, puede afectar a la calidad de la señal. Algunas estrategias para mejorar la comunicación vehicular en este tipo de entorno consiste en desplegar UAVs o vehículo aéreo no tripulado (drones), los cuales actúan como enlaces de comunicación entre vehículos. De hecho, UAV ofrece importantes ventajas de implementación, ya que tienen una gran flexibilidad en términos de movilidad, además de un rango de comunicaciones mejorado. Para evaluar la calidad de las comunicaciones, debe realizarse un conjunto de mediciones. Sin embargo, debido al costo de las implementaciones reales de UAV y automóviles, los experimentos reales podrían no ser factibles para actividades de investigación con recursos limitados. Por lo tanto, los experimentos de simulación se convierten en la opción preferida para evaluar las comunicaciones entre UAV y vehículos terrestres. Lograr modelos de propagación de señal correctos y representativos que puedan importarse a los entornos de simulación se vuelve crucial para obtener un mayor grado de realismo, especialmente para simulaciones que involucran el movimiento de UAVs en cualquier lugar del espacio 3D. En particular, la información de elevación del terreno debe tenerse en cuenta al intentar caracterizar los efectos de propagación de la señal. En esta tesis doctoral, proponemos nuevos enfoques tanto teóricos como empíricos para estudiar la integración de redes vehiculares que combinan automóviles y UAVs, así mismo el impacto del entorno en la calidad de las comunicaciones. Esta tesis presenta una aplicación, una metodología de medición en escenarios reales y un nuevo modelo de simulación, los cuales contribuyen a modelar, desarrollar e implementar servicios C-ITS. Más específicamente, proponemos un modelo de simulación que tiene en cuenta las características del terreno en 3D, para lograr resultados confiables de comunicación entre UAV y vehículos terrestres.
[CAT] Per a proporcionar un entorn de trànsit viari més segur i eficient, els sistemes ITS o Sistemes Intel·ligents de Transport representen una solució dotada d'avanços tecnològics d'avantguarda. La integració d'elements de transport com auto móvils juntament amb elements d'infraestructura com Road Side Units (RSUs) situats al llarg de lav via de comunicació permeten oferir un entorn de xarxa connectat amb multiples serveis, inclusa connectivitat a Internet. Aquesta integració es connex amb el terme C-ITS o Sistemes Intel·ligents de Transport Cooperatius , com ara els automòbils, amb elements d'infraestructura, com ara les road side units (RSU) o pals situats al llarg de la carretera, per a aconseguir un entorn de xarxa que oferisca nous serveis a més de connectivitat a Internet. Aquesta integració s'expressa amb el terme C-ITS, o sistemes intel·ligents de transport cooperatius. La connexió d'automòbils amb dispositius d'infraestructura permet crear xarxes vehiculars connectades (V2X) vehicle a dispositiu, que ofreixen la possibilitat de nous desplegaments en aplicacions C-ITS, com ara les relacionades amb la seguretat. Avui dia, amb l'ús massiu dels telèfons intel·ligents, i a causa de la flexibilitat i mobilitat que presenten, es fan esforços per integrar-los amb els automòbils. De fet, amb el suport adequat d'unitat a bord (OBU), els telèfons intel·ligents es poden integrar perfectament amb les xarxes vehiculars, permetent als conductors usar els seus telèfons intel·ligents com a dispositius per a participar en els serveis de C-ITS, a fi de millorar la seguretat al volant entre altres. Tòpic est, que hui dia representa un tema rellevant d'investigació. Un problema a solucionar sorgeix quan les comunicacions vehiculars ateixen inferències i bloquejos del senyal deguts a l'escenari. De fet, l'impacte de la vegetació i els edificis, tant en àrees urbanes com rurals, pot afectar la qualitat del senyal. Algunes estratègies de millorar la comunicació vehicular en aquest tipus d'entorn consisteix a desplegar UAVs o vehicles aeris no tripulats (drones), els quals actuen com a enllaços de comunicació entre vehicles. De fet, l'ús d'UAVs ofereix importants avantatges d'implementació, ja que tenen una gran flexibilitat en termes de mobilitat, a més d'un rang de comunicacions millorat. Per a avaluar la qualitat de les comunicacions, s'han de realitzar mesures en escenaris reals. No obstant això, a causa del cost de les implementacions i desplegaments reals d'UAV i el seu ús combinat amb vehicles, aquests experiments reals podrien no ser factibles per a activitats d'investigació amb recursos limitats. Per tant, la metodologia basada en simulació es converteixen en l'opció preferida entre els investigadors per a avaluar les comunicacions entre UAV i vehicles terrestres. Aconseguir models de propagació de senyal correctes i representatius que puguen importar-se als entorns de simulació resulta crucial per a obtenir un major grau de realisme, especialment per a simulacions que involucren el moviment d'UAV en qualsevol lloc de l'espai 3D. En particular, cal tenir en compte la informació d'elevació del terreny per a intentar caracteritzar els efectes de propagació del senyal. En aquesta tesi doctoral proposem enfocaments tant teòrics com empírics per a estudiar la integració de xarxes vehiculars que combinen automòbils i UAV, així com l'impacte de l'entorn en la qualitat de les comunicacions. Aquesta tesi presenta una aplicació, una metodología de mesurament en escenaris reals i un nou model de simulació, els quals contribueixen a modelar, desenvolupar i implementar serveis C-ITS. Més específicament, proposem un model de simulació que té en compte les característiques del terreny en 3D, per a aconseguir resultats fiables de comunicació entre UAV i vehicles terrestres.
[EN] To provide a safer road traffic environment and make it more convenient, Intelligent Transport Systems (ITSs) are proposed as a solution endowed with cutting-edge technological advances. The integration of transportation elements like cars together with infrastructure elements like Road Side Units to achieve a networking environment offers new services in addition to Internet connectivity. This integration comes under the term Cooperative Intelligent Transport System (C-ITS). Connecting cars with surrounding devices forming vehicular networks in Vehicle-to-Everything (V2X) open new deployments in C-ITS applications like safety-related ones. With the massive use of smartphones nowadays, and due to their flexibility and mobility, several efforts exist to integrate them with cars. In fact, with the right support from the vehicle's On-Board Unit (OBU), smartphones can be seamlessly integrated with vehicular networks. Hence, drivers can use their smartphones as a device to participate in C-ITS services for safety purposes, among others, which is a quite interesting research topic. A significant problem arises when vehicular communications face signal obstructions caused by the environment. In fact, the impact of vegetation and buildings, whether in urban and rural areas, can result in a lower signal quality. One way to enhance vehicular communication networks is to deploy Unmanned Aerial Vehicles (UAVs) to act as relays for communication between cars, or ground vehicles. In fact, UAVs offer important deployment advantages, as they offer great flexibility in terms of mobility, in addition to an enhanced communications range. To assess the quality of the communications, a set of measurements must take place. However, due to the cost of real deployments of UAVs and cars, real experiments might not be feasible for research activities with limited resources. Hence, simulation experiments become the preferred option to assess UAV-to- car communications. Achieving correct and representative signal propagation models that can be imported to the simulation environments becomes crucial to obtain a higher degree of realism, especially for simulations involving UAVs moving anywhere throughout the 3D space. In particular, terrain elevation information must be taken into account when attempting to characterize signal propagation effects. In this research work, we propose both theoretical and empirical approaches to study the integration of vehicular networks combining cars and UAVs, and we study the impact of the surrounding environment on the communications quality. An application, a measurement framework, and a simulation model are presented in this thesis in an effort to model, develop, and deploy C-ITS services. More specifically, we propose a simulation model that takes into account 3D terrain features to achieve reliable UAV-to-car communication results.
I want to thank the Spanish government through the Ministry of Economy and Competitiveness (MINECO) and the European Union Commission through the European Social Fund (ESF) for co-financing and granting me the fellowship to fund my studies in Spain and my research stay in Russia. In addition, I would to thank the National Institute of Informatics for granting me the internship fund and the Japanese government through the Japan Society for the Promotion of Science (JSPS) for supporting my research work in Japan.
Hadiwardoyo, SA. (2019). Modelling and Real Deployment of C-ITS by Integrating Ground Vehicles and Unmanned Aerial Vehicles [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/118796
TESIS

Traffic congestion and safety has become a major issue in the modern world's commute. Congestion has been causing people to travel billions of hours more and to purchase billions of gallons of fuel extra which account to congestion cost of billions of dollars. Autonomous driving vehicles have been one solution to this problem because of their huge impact on efficiency, pollution, and human safety. Also, extensive research has been carried out on control design of vehicular platoons because a further improvement in traffic throughput while not compromising the safety is possible when the vehicles in the platoon are provided with better predictive abilities. Motion control is a key area of autonomous driving research that handles moving parts of vehicles in a deliberate and controlled manner. A widely worked on problem in motion control concerned with time parameterized reference tracking is trajectory tracking. Having an efficient and effective tracking algorithm embedded in the autonomous driving system is the key for better performance in terms of resources consumed and tracking error. Many tracking control algorithms in literature rely on an accurate model of the vehicle and often, it can be an intimidating task to come up with an accurate model taking into consideration various conditions like friction, heat effects, ageing processes etc. And typically, control algorithms rely on periodic execution of the tasks that update the control actions, but such updates might not be required, which result in unnecessary actions that waste resources. The main focus of this work is to design an intermittent model-free optimal control algorithm in order to enable autonomous vehicles to track trajectories at high-speeds. To obtain a solution which is model-free, a Q-learning setup with an actor-network to approximate the optimal intermittent controller and a critic network to approximate the optimal cost, resulting in the appropriate tuning laws is considered.
Master of Science
A risen research effort in the area of autonomous vehicles has been witnessed in the past few decades because these systems improve safety, comfort, transport time and energy consumption which are some of the main issues humans are facing in the modern world’s highway systems. Systems like emergency braking, automatic parking, blind angle vehicle detection are creating a safer driving environment in populated areas. Advanced driver assistance systems (ADAS) are what such kind of systems are known as. An extension of these partially automated ADAS are vehicles with fully automated driving abilities, which are able to drive by themselves without any human involvement. An extensively proposed approach for making traffic throughput more efficient on existing highways is to assemble autonomous vehicles into platoons. Small intervehicle spacing and many vehicles constituting each platoon formation improve the traffic throughput significantly. Lately, the advancements in computational capabilities, in terms of both algorithms and hardware, communications, and navigation and sensing devices contributed a lot to the development of autonomous systems (both single and multiagent) that operate with high reliability in uncertain/dynamic operating conditions and environments. Motion control is an important area in the autonomous vehicles research. Trajectory-tracking is a widely studied motion control scenario which is about designing control laws that force a system to follow some time-dependent reference path and it is important to have an effective and efficient trajectory-tracking control law in an autonomous vehicle to reduce the resources consumed and tracking error. The goal of this work is to design an intermittent model-free trajectory tracking control algorithm where there is no need of any mathematical model of the vehicle system being controlled and which can reduce the controller updates by allowing the system to evolve in an open loop fashion and close the loop only when an user defined triggering condition is satisfied. The approach is energy efficient in that the control updates are limited to instances when they are needed rather than unnecessary periodic updates. Q-learning which is a model-free reinforcement learning technique is used in the trajectory tracking motion control algorithm to make the vehicles track their respective reference trajectories without any requirement of their motion model, the knowledge of which is generally needed when dealing with a motion control problem. The testing of the designed algorithm in simulations and experiments is presented in this work. The study and development of a vehicle platform in order to perform the experiments is also discussed. Different motion control and sensing techniques are presented and used. The vehicle platform is shown to track a reference trajectory autonomously without any human intervention, both in simulations and experiments, proving the effectiveness of the proposed algorithm.

This thesis describes the research activity carried out on the navigation of unmanned ground vehicles in outdoor unstructured environments. These environments are very common in a wide variety of real-application scenarios, such as search and rescue for post-disaster response, monitoring of the environment and industrial facilities, precision farming, planetary exploration etc.. For this reason, robotics researchers have been investigating such kind of environments for decades. However, the problem of vehicle navigation in these scenarios is not fully solved. In fact, a general approach for ground vehicle motion planning, taking into account both the robot and the environment features, is still far to be defined. In the literature, this problem has been addressed through the so-called traversability analysis. It can be seen as an assessment of the difficulty for a specific ground vehicle, characterized by its own locomotion features, to cross a terrain area, which is in turn characterized by its own morphology and appearance. The works reported in this thesis are related to the problem of geometry-based traversability analysis. It consists in deriving maps of traversing costs from three-dimensional models of the environment. These costmaps are extremely useful in challenging environments, as they are used in robot motion planning to avoid unsafe paths for the vehicle itself. Still in the context of 3D reconstructions, a solution for the remote drive of mobile robotic platforms has been developed. The aim has been to enhance the operator interface with helpful information, including traversing costs, via graphical elements presented in a mixed reality context. Finally, coverage path planning for unmanned aerial vehicles has been investigated as well. It is a specific kind of path planning related to three-dimensional photogrammetric reconstruction. In particular, an approach to manage a flock of aerial vehicles has been developed, in order to parallelize the coverage mission. The coverage task is the first step needed for the environment reconstruction. Eventually the traversability analysis can be performed on the obtained reconstruction. Experimental and on-field trials have also been performed on a real mobile robotic platform, for the testing of the proposed approaches. The results achieved are reported and widely discussed.

Unmanned Ground Vehicles (UGVs) play a vital role in preserving human life during hostile military operations and extend our reach by exploring extraterrestrial worlds during space missions. These systems generally have to operate in unstructured environments which contain dynamic variables and unpredictable obstacles, making the seemingly simple task of traversing from A-B extremely difficult. Terrain is one of the biggest obstacles within these environments as it could potentially cause a vehicle to become stuck and render it useless, therefore autonomous systems must possess the ability to directly sense terrain conditions. Current autonomous vehicles use look-ahead vision systems and passive laser scanners to navigate a safe path around obstacles; however these methods lack detail when considering terrain as they make predictions using estimations of the terrain’s appearance alone. This study establishes a more accurate method of measuring, classifying and monitoring terrain in real-time. A novel instrument for measuring direct terrain features at the wheel-terrain contact interface is presented in the form of the Force Sensing Wheel (FSW). Additionally a classification method using unique parameters of the wheel-terrain interaction is used to identify and monitor terrain conditions in real-time. The combination of both the FSW and real-time classification method facilitates better traversal decisions, creating a more Terrain Capable system.

Autonomous vehicle development is a rapidly growing field that has vast possibilities for both military and commercial applications. Removing people from dangerous tasks will save lives. Continued research is necessary in order to build these new technologies and mature those already established. One area of potential in the unmanned vehicle community is that of fully autonomous cooperation. This area of research will allow multiple unmanned platforms to perform new functions on a larger scale by combining their capabilities in a coordinated manner. This thesis addresses the emerging need of research related to fully autonomous cooperation between a heterogeneous team of vehicles, by taking a system level approach and integrating the necessary technologies. Software was developed and then tested that combines an unmanned ground vehicle and an unmanned aerial vehicle in order to perform a task that utilizes the strengths of each platform. The ground vehicle is programmed with a route for which it sends look-ahead waypoints to the aircraft. As it traverses the route, the aircraft searches for possible targets. If a target is detected, the approximate coordinates are sent over the network and the ground vehicle then further localizes and inspects the target. Once the inspection is completed, the ground vehicle continues on its previous route. This thesis demonstrates that pairing ground and aerial vehicles in a fully autonomous target localization problem can indeed provide a team functioning more efficiently than either alone.
Master of Science

Reissued 2 Mar 2015 to correct degree earned
Approved for public release; distribution is unlimited
Reissued 2 Mar 2015 to correct degree earned
Technological advances and research are pushing the application of unmanned vehicles in exciting directions. This thesis emphasis is on cost estimation for a new unmanned aerial vehicle (UAV) with swarm applications. The new swarm UAV theoretical can be designed to emulate the current unmanned aerial system (UAS) mission, and expand upon the communication relay mission. Small UASs have a line-of-sight capability limitation that leaves room for improvement. The UAVs organic to the U.S. Marine Corps (USMC) are the primary focus for this analysis because organic USMC UAVs are habitually small UAVs. The analysis will determine a rough cost estimation range for a future AV with new technology. Based on the adaptation of networking topologies and research, the communication relay mission is a feasible capability to Peruse in future swarm UAVs. The analysis suggests that a swarm UAV is comparable in cost to legacy UAVs currently in service in the USMC.

Thesis (M.S.)--West Virginia University, 2008.
Title from document title page. Document formatted into pages; contains x, 141 p. : ill. (some col.). Includes abstract. Includes bibliographical references (p. 76-78).

Autonomous navigation of mobile robots through unstructured terrain presents many challenges. The task becomes even more difficult with increasing obstacle density, at higher speeds, and when a priori knowledge of the terrain is not available. Reactive navigation schemas are often dismissed as overly simplistic or considered to be inferior to deliberative approaches for off-road navigation. The Potential Field algorithm has been a popular reactive approach for low speed, highly maneuverable mobile robots. However, as vehicle speeds increase, Potential Fields becomes less effective at avoiding obstacles. The traditional shortcomings of the Potential Field approach can be largely overcome by using dynamically expanding perception zones to help track objects of immediate interest. This newly developed technique is hereafter referred to as the Dynamic Expanding Zones (DEZ) algorithm. In this approach, the Potential Field algorithm is used for waypoint navigation and the DEZ algorithm is used for obstacle avoidance. This combination of methods facilitates high-speed navigation in obstaclerich environments at a fraction of the computational cost and complexity of deliberative methods. The DEZ reactive navigation algorithm is believed to represent a fundamental contribution to the body of knowledge in the area of high-speed reactive navigation. This method was implemented on the Virginia Tech DARPA Grand Challenge vehicles. The results of this implementation are presented as a case study to demonstrate the efficacy of the newly developed DEZ approach.
Master of Science

Current trends in agricultural equipment have led to an increasing degree of autonomy. As the state of the art progresses towards fully autonomous vehicles, it is important to consider assumptions implicit in the design of these vehicles. Current automation in harvesters have led to increased sensing and automation on current combines, but no published research examines the effect of machine size on the viability of the autonomous system. The question this thesis examines is: if a human is no longer required to operate an individual harvester, is it possible to build smaller equipment that is still economically viable? This thesis examines the appropriateness of automating these machines by developing a conceptual model for smaller, fully autonomous harvesters. This model includes the basic mechanical subsystems, a conceptual software design, and an economic model of the total cost of ownership. The result of this conceptual design and analysis is a greater understanding of the role of autonomy in harvest. By comparing machine size, machine function, and the costs to own and operate this equipment, design guidelines for future autonomous systems are better understood. It is possible to build an autonomous harvesting system that can compete with current technologies in both harvest speed and overall cost of ownership.
Master of Science

The objective of this study was to determine which size symbols should be used by the U.S. Army for an operator control unit to indicate the status of unmanned ground vehicles (UGVs). Three sizes of symbols were studied. The symbols subtended 20, 40, and 69 minutes of arc corresponding to 0.116, 0.233, and 0.400 inches high when viewed at a distance of 20 inches from a touch screen. Twelve participants were asked to watch the symbols on a map display and touch one of four UGV symbols when it stopped moving. Different numbers (0, 8 and 12) of distracter symbols with the same height as the UGV symbols appeared during the experimental trials. The time to notice that a UGV symbol had stopped (recognition time) and to touch the screen (response time) were measured. Participants were asked for Subjective Workload Assessment Technique (SWAT) ratings for each combination of symbol size and number of distracter symbols. Errors committed while attempting to touch the correct symbol were counted. Participants made very few errors attempting to touch the wrong symbol. Results for the time and error measures were as expected for changes in symbol size. As symbol size increased, recognition time, response time, and extra touches decreased. Significant differences were seen in these measures between the subtending 20 and 40 minutes of arc and between symbols subtending 20 and 69 minutes of arc. Also, as expected, subjective mental workload increased as symbol size decreased with differences seen between all symbol size levels. No significant differences were observed for workload manipulation (number of distracter symbols) as measured by time and error. However, SWAT scores did show a significant difference as a result of number of distracters. The differences between 0 and 8 distracters and between 0 and 12 distracters were significant. There was no significant interaction between symbol size and number of distracters for any of the measures. Overall results suggest that symbols smaller than those recommended for keypads may be sufficient for interactive map displays. For static platforms with barehanded operators, symbols that subtend 40 minutes of arc may be sufficiently large to ensure adequate touch screen performance under low to moderate workload conditions.
Master of Science

Thesis (M.S.)--West Virginia University, 2006.
Title from document title page. Document formatted into pages; contains x, 100 p. : ill. (some col.). Includes abstract. Includes bibliographical references (p. 83-86).

Due to the limitations of GPS in areas where line of sight to the sky is obstructed the development of a GPS-free algorithm for relative formation control is an asset to collaborative vehicles. This paper presents a novel approach based on the Received Signal Strength Indication (RSSI) measurement between broadcast and receive nodes to calculate distance and using the data transfer capability to allow each vehicle to develop a table of relative positions. These relative positions are used to create a potential field that results in an absolute minimum at the vehicles desired position. All vehicles are numbered sequentially. The numbering defines the order in which they will broadcast their data, as well as their position along the perimeter. This thesis looks at two control methods for achieving a formation. The first is the circular motion method that puts perimeter nodes in an orbit around around the perimeter center. The second is a gradient descent method that calculates the gradient of the potential field. Both methods achieve a formation when all perimeter nodes are at their absolute minimums in the potential field. Tests were conducted to analyze RSSI measurements using the 802.15.4 protocol, and a mathematical simulation was conducted for each control algorithm.
Master of Science

Unmanned Ground Vehicles (UGVs) are becoming more widespread in their deployment. Advances in technology have improved not only their reliability but also their ability to perform complex tasks. UGVs are particularly attractive for operations that are considered unsuitable for human operatives. These include dangerous operations such as explosive ordnance disarmament, as well as situations where human access is limited including planetary exploration or search and rescue missions involving physically small spaces. As technology advances, UGVs are gaining increased capabilities and consummate increased complexity, allowing them to participate in increasingly wide range of scenarios. UGVs have limited power reserves that can restrict a UGV’s mission duration and also the range of capabilities that it can deploy. As UGVs tend towards increased capabilities and complexity, extra burden is placed on the already stretched power resources. Electric drives and an increasing array of processors, sensors and effectors, all need sufficient power to operate. Accurate prediction of mission power requirements is therefore of utmost importance, especially in safety critical scenarios where the UGV must complete an atomic task or risk the creation of an unsafe environment due to failure caused by depleted power. Live energy prediction for vehicles that traverse typical road surfaces is a wellresearched topic. However, this is not sufficient for modern UGVs as they are required to traverse a wide variety of terrains that may change considerably with prevailing environmental conditions. This thesis addresses the gap by presenting a novel approach to both off and on-line energy prediction that considers the effects of weather conditions on a wide variety of terrains. The prediction is based upon nonlinear polynomial regression using live sensor data to improve upon the accuracy provided by current methods. The new approach is evaluated and compared to existing algorithms using a custom ‘UGV mission power’ simulation tool. The tool allows the user to test the accuracy of various mission energy prediction algorithms over a specified mission routes that include a variety of terrains and prevailing weather conditions. A series of experiments that test and record the ‘real world’ power use of a typical small electric drive UGV are also performed. The tests are conducted for a variety of terrains and weather conditions and the empirical results are used to validate the results of the simulation tool. The new algorithm showed a significant improvement compared with current methods, which will allow for UGVs deployed in real world scenarios where they must contend with a variety of terrains and changeable weather conditions to make accurate energy use predictions. This enables more capabilities to be deployed with a known impact on remaining mission power requirement, more efficient mission durations through avoiding the need to maintain excessive estimated power reserves and increased safety through reduced risk of aborting atomic operations in safety critical scenarios. As supplementary contribution, this work created a power resource usage and prediction test bed UGV and resulting data-sets as well as a novel simulation tool for UGV mission energy prediction. The tool implements a UGV model with accurate power use characteristics, confirmed by an empirical test series. The tool can be used to test a wide variety of scenarios and power prediction algorithms and could be used for the development of further mission energy prediction technology or be used as a mission energy planning tool.

In this paper I describe a motion planning technique for intelligent ground vehicles. The technique is an implementation of a path selection algorithm based on fuzzy inference. The approach extends on the motion planning algorithm known as driving with tentacles. The selection of the tentacle (a drivable path) to follow relies on the calculation of a weighted cost function for each tentacle in the current speed set, and depends on variables such as the distance to the desired position, speed, and the closeness of a tentacle to any obstacles. A Matlab simulation and the practical implementation of the fuzzy inference rule on a Clearpath Husky robot within the Robot Operating System (ROS) framework are provided.

Unmanned aerial vehicle (UAV) technology was used to determine tidal extent in Kimages Creek, a restored tidal wetland located in Charles City County, Virginia. A Sensefly eBee Real-Time Kinematic UAV equipped with the Sensor Optimized for Drone Applications (SODA) camera (20-megapixel RGB sensor) was flown during a single high and low tide event in Summer 2017. Collectively, over 1,300 images were captured and processed using Pix4D. Horizontal and vertical accuracy of models created using ground control points (GCP) ranged from 0.176 m to 0.363 m. The high tide elevation model was subtracted from the low tide using the ArcMap 10.5.1 raster calculator. The positive difference was displayed to show the portion of high tide that was above the low tide. These results show that UAVs offer numerous spatial and temporal advantages, but further research is needed to determine the best method of GCP placement in areas of similar forest structure.

Unmanned vehicle systems, specifically Unmanned Air Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) have found potential use in both military and civilian applications. For many applications, unmanned vehicle systems are required to navigate in urban environments where obstacles with various types and sizes exist. The main contribution of this research is to offer vision-based path planning, collision avoidance, and target tracking strategies for Unmanned Air and Ground vehicles operating in urban environments. Two vision-based local-level frame mapping and planning techniques are first developed for Miniature Air Vehicles (MAVs). The techniques build maps and plan paths in the local-level frame of MAVs directly using the camera measurements without transforming to the inertial frame. Using a depth map of an environment obtained by computer vision methods, the first technique employs an extended Kalman Filter (EKF) to estimate the range, azimuth to, and height of obstacles, and constructs local spherical maps around MAVs. Based on the maps, the Rapidly-Exploring Random Tree (RRT) algorithm is used to plan collision-free Dubins paths. The second technique constructs local multi-resolution maps using an occupancy grid, which give higher resolution to the areas that are close to MAVs and give lower resolution to the areas that are far away. The maps are built using a log-polar representation. The two planning techniques are demonstrated in simulation and flight tests. Based on the observation that a camera does not provide accurate time-to-collision (TTC) measurements, two and three dimensional observability-based planning algorithms are explored. The techniques estimate both TTC and bearing using bearing-only measurements. A nonlinear observability analysis of state estimation process is conducted to obtain the conditions for complete observability of the system. Using the conditions, the observability-based planning algorithms are designed to minimize the estimation uncertainties while simultaneously avoiding collisions. The two dimensional planning algorithm parameterizes an obstacle using TTC and azimuth, and constructs local polar maps. The three dimensional planning algorithm parameterizes an obstacle using inverse TTC, azimuth, and elevation, and constructs local spherical maps. The algorithms are demonstrated in simulation. Lastly, a probabilistic path planning algorithm is developed for tracking a moving target in urban environments using UAVs and UGVs. The algorithm takes into account occlusions due to obstacles. It models the target using a dynamic occupancy grid and updates the target location using a Bayesian filter. Based on the target's current and probable future locations, a decentralized path planning algorithm is designed to generate suboptimal paths that maximize the sum of the joint probability of detection for all vehicles over a finite look-ahead horizon. Results demonstrate the planning algorithm is successful in solving the moving target tracking problem in urban environments.

Perception is a key feature in how any creature or autonomous system relates to its environment. While there are many types of perception, this thesis focuses on the improvement of the visual robotics perception systems. By implementing a broadband passive sensing system in conjunction with current perception algorithms, this thesis explores scene reconstruction and world modeling.
The process involves two main steps. The first is stereo correspondence using block matching algorithms with filtering to improve the quality of this matching process. The disparity maps are then transformed into 3D point clouds. These point clouds are filtered again before the registration process is done. The registration uses a SAC-IA matching technique to align the point clouds with minimum error.  The registered final cloud is then filtered again to smooth and down sample the large amount of data. This process was implemented through software architecture that utilizes Qt, OpenCV, and Point Cloud Library. It was tested using a variety of experiments on each of the components of the process.  It shows promise for being able to replace or augment existing UGV perception systems in the future.
Master of Science

Unmanned Aerial Vehicles (UAV) are expected to be deployed both by government and industry. Rules for integrating commercial UAVs into a nation's airspace still need to be defined, safety being the main concern. As part of this thesis, the communication needs of UAVs as important requirement for UAV integration into the national airspace is considered. Motivated by recent prediction of UAV quantities, revealing the importance of Micro UAVs (MAV) and Small UAVs (SUAV), the thesis determines spectral requirements for control and non-payload communication (CNPC). We show that spectral efficiency, particularly in the downlink, is critical to the large-scale deployment of UAVs. Due to the limited range of small SUAV and MAV systems, communication between air and ground elements of these UAVs is established through radio Line-of-Sight (LoS) links. Ultimately, efficient LoS UAV systems are based on a better understanding of channels in the downlink, i.e. air-to-ground (A2G) channels, and also on efficient waveform as well as spectrum management implementation. Because of limited research in wideband aeronautical channel modeling, we have derived an A2G channel prototype applicable to SUAV and MAV. As part of the research at Wire- less@VT in designing and prototyping Orthogonal Frequency Division Multiplexing (OFDM) waveforms, this thesis derives the optimal parameters for SUAV and MAV A2G channels. Finally, the thesis discusses concepts that relate flight route with spectrum management as well as opportunities for a more dynamic spectrum allocation for UAV communication systems.
Master of Science

The problem of roadway navigation and obstacle avoidance for unmanned ground vehicles has typically needed very expensive sensing to operate properly. To reduce the cost of sensing, it is proposed that an algorithm be developed that uses a single visual camera to image the roadway, determine where the lane of travel is in the image, and segment that lane. The algorithm would need to be as accurate as current lane finding algorithms as well as faster than a standard k- means segmentation across the entire image. This algorithm, named IRIS, was developed and tested on several sets of roadway images. The algorithm was tested for its accuracy and speed, and was found to be better than 86% accurate across all data sets for an optimal choice of algorithm parameters. IRIS was also found to be faster than a k-means segmentation across the entire image. IRIS was found to be adequate for fulfilling the design goals for the algorithm. IRIS is a feasible system for lane identification and segmentation, but it is not currently a viable system. More work to increase the speed of the algorithm and the accuracy of lane detection and to extend the inherent lane model to more complex road types is needed. IRIS represents a significant step forward in the single camera roadway perception field.
Master of Science

Veículos autônomos são objeto de crescente estudo em todo o mundo. Face à Engenharia de Transportes, é tema que deve provocar uma revolução nas próximas décadas, pois é concreta a tendência ao uso destes veículos na sociedade. Podem se citar como grandes beneficiados a segurança, a logística, o fluxo de trânsito, o meio ambiente e também os portadores de deficiências. Com o objetivo de fazer um veículo atingir um ponto com coordenadas conhecidas de forma autônoma, uma plataforma veicular terrestre em escala foi utilizada, a qual recebeu um sistema computacional micro controlado e tecnologias para proporcionar mobilidade através de motores elétricos para tração e servo-motores para direcionamento; posicionamento por satélite através de receptor GNSS e bússola eletrônica para orientação; sensoriamento por ultra-som para evitar colisões; e comunicação sem fio, a fim de se realizar remotamente monitoramento e instrução em tempo real através de um aplicativo para computador pessoal (PC). Foi desenvolvido um algoritmo de navegação que, fazendo uso dos recursos disponíveis, proporcionou autonomia ao veículo, de forma a navegar para pontos com coordenadas conhecidas sem controle humano. Os testes realizados visaram avaliar a capacidade de autonomia do veículo, a trajetória de navegação realizada e a acurácia de chegada aos pontos de destino. O veículo foi capaz de atingir os pontos em todos os testes realizados, sendo considerado funcional seu algoritmo de navegação e também os sistemas de mobilidade, posicionamento, sensoriamento e comunicação.
Autonomous vehicles are an on growing research target around the world. Face to Transports Engineering, it is a subject which is expected to make a revolution on the next decades. The great benefits are on security, logistic, traffic flow, environment and handicap. With the goal to make a vehicle navigate autonomously to known geodesics coordinates, a reduced scale terrestrial vehicular platform was used. This platform received a microcontrolled computational system and technologies to give it mobility, through electrical motors for traction and servo-motors for direction; satellite positioning, through a GNSS receiver and magnetic compass for orientation; ultrasound sensing in order to avoid collision; and wireless communication, in order to do remote monitoring and instruction at real time through a PC application. It was developed a navigation algorithm which, from the available resources, gave autonomy to the vehicle, in order to navigate to known geodesics coordinates without human control. The test set was intended to evaluate the autonomy capacity of the vehicle, the navigation trajectory that was done and the arrival accuracy to the destination points. The vehicle reached the destination points on all tests done, being evaluated as functional its navigation algorithm and also the mobility, positioning, sensing and communication systems.

Historiskt har soldater till fots burit sin personliga utrustning till fots. Den övriga utrustning som soldaten behövde transporterades ofta i vagnar dragna av olika dragdjur. Då stridstempot och framförallt framryckningshastigheten har ökat, har behovet av att bära med sig all nödvändig utrustning ökat. I takt med att nya system tillförts, har därmed också den burna vikten för den enskilde soldaten ökat. Undersökningen har genomförts som en komparativ studie av olika typer av obemannade markfarkoster, så kallade UGV-system, genom att deras möjligheter och begränsningar har analyserats och jämförts utifrån de krav som ställs av scenariot, och av den militära användaren, vid lösandet av en specifik taktisk uppgift. Kriterierna för jämförelse har med hjälp av konceptet militär nytta, framtaget av Andersson et al (2015), tagits fram ur scenariot. Studien kan konstatera att den militära nyttan med dessa UGV-system är att soldaternas egen rörlighet och uthållighet ökar, samtidigt som den skaderisk som tunga bördor innebär minskar. En soldat som inte är utmattad efter att ha burit tung utrustning har en högre stridsberedskap och agerar med större skärpa. Förbandens operativa rörlighet och uthållighet ökar också och beroende på vilket UGV-system som används återfinns olika grader av militär nytta.
Historically, soldiers on foot have carried their personal equipment. Other equipment that the soldier needed was often transported in wagons drawn by different beasts of burden. As the high operational tempo, and above all, forward speed has increased, the need to carry all necessary equipment also has grown. And, as new systems have been added, the load to carry for the individual soldier has thus increased. The survey has been conducted as a comparative study of different types of unmanned ground vehicles, so-called UGV systems, by analyzing their possibilities and limitations based on the requirements of the scenario and also the requirements by the military user in solving a specific tactical task. The criteria for comparison have been developed from the scenario using the concept of military utility, developed by Andersson et al. (2015). The study concludes that the military benefits connected to the UGV systems are that the individual mobility and endurance of the soldiers increases, and that the risk of injuries from carrying heavy loads decreases. A soldier not exhausted from carrying heavy loads has a higher combat preparedness and acts with greater focus. The operational mobility and endurance of the unit also increases and, depending on which UGV systems are used, different degrees of military benefit are to be found.

In the broadest sense, an Unmanned Ground Vehicle (UGV) is any piece of mechanized equipment that moves across the surface of the ground and serves as a means for carrying or transporting something, but explicitly does not carry a human being. The main parts of UGV are: sensors, platform, control, human machine interface, communication and system integration.

International Telemetering Conference Proceedings / October 18-21, 2004 / Town & Country Resort, San Diego, California
This paper describes a system of Total Border Surveillance, which is cost effective, closes existing gaps and is less manpower intensive than the current techniques. The system utilizes a fleet of commercially available aircraft converted to unmanned capability, existing GPS and surveillance systems and autonomous ground stations to provide the desired coverage.

Obemannade markfarkoster är ännu ganska ovanliga i den svenska Försvarsmakten men borde kunna bli allt vanligare. UGV:er används traditionellt till att utföra smutsiga, tråkiga och farliga arbetsuppgifter. Kan de då vara användbara i Afghanistan mot den motståndare som FM möter där idag? I studien undersöker författaren möjligheterna för obemannade markfarkoster att bidra med militär nytta inom området logistiktransporter. De obemannade transportfordonen kan från grunden utgöras av standardlastbilar i FM som har utrustats med så kallade UGV-kit. Dessa UGV-kit har till uppgift att göra standardfordonen fjärrstyrda, autonoma eller både och. Samma princip gäller för eskortfordonen som följer med till stöd för logistiktransporten, en Galt ska exempelvis kunna agera UGV. Den irreguljära och lågteknologiska motståndaren använder ofta IED:er vid eldöverfall vilket har gjort landsvägstransporter till riskfylld verksamhet för personal ute på vägarna. Personalsäkerhet är prioriterad verksamhet i Försvarsmakten och författarens antagande är att UGV:er kan bidra till att göra logistiktransporter och eskortförfaranden till mindre riskabel verksamhet.
Unmanned ground vehicles are still quite rare within in the Swedish Armed Forces but they should become more common. UGV´s are used traditionally for performing dirty, dull and dangerous tasks. Could they also be usefull against the enemy in Afghanistan that the Swedish Armed Forces are confronting there today? In this study the author investigates the possibilities for unmanned ground vehicles to contribute with military benefits to the area of logistics transportation. The unmanned transport vehicles can be ordinary standard trucks from the beginning which have been equipped with a so called UGV-kit. This UGV-kit´s task is to make the standard vehicles remotely controlled, autonomous or both. The same principle applies to the escorting vehicles, a Galt should for example also be able to act as a UGV. The irregular and low technology enemy often uses IED’s when attacking, which have made road transportation to hazardous activities for the personnel on the road. Personnel safety are prioritized activity within the Swedish Armed Forces, and the authors assumtion is that UGV’s can help making logistics transportation and escorting procedures in to less risky activities.

Le progrès génétique est l'un des principaux leviers utilisés pour accroître la production alimentaire et nourrir la population humaine croissante dans un contexte de changement global. La sélection ou la création du cultivar optimal pour un endroit donné est très difficile compte tenu de la très grande variabilité spatiale et temporelle des conditions environnementales. Le phénotypage au champ, c'est-à-dire le suivi quantitatif des variables d'état des cultures et du fonctionnement du couvert, a été reconnu comme le goulot d'étranglement pour accélérer le progrès génétique. Dans cette thèse pluridisciplinaire, des méthodes statistiques et de traitement d’images sont développées afin d’estimer différents traits structuraux de cultures de blé pour application à l’amélioration variétale. Cette thèse a été entreprise au moment où la technologie progresse très rapidement, à la fois sur les aspects matériels et logiciels : accessibilité aux plates-formes de drones et de véhicules sans pilote, diminution du coût des unités de traitement graphique (GPU) explosion du développement des algorithmes d'apprentissage profond. Cette thèse s’articule en cinq chapitres : Le premier chapitre introduit les motivations de l’étude ainsi que les besoins actuel en matière de phénotypage haut débit. Un état de l’art sur le phénotypage est aussi présenté en attirant l’attention sur les méthodes de traitements d’images et de réseaux de neurones convolutifs. Le deuxième chapitre présente le développement de méthodologies permettant d’estimer la hauteur du couvert à partir d’observations par drone ou par robot roulant au sol. La faisabilité de deux principales technologies et plateformes ont été comparées et prouvées: le LiDAR porté par un véhicule au sol et des images RVB acquises par drone. Les deux chapitres suivants adressent le problème de l’estimation de la densité d’épis et de tiges de blé par images à haute résolution spatiale. Les résultats montrent le potentiel et les limites de l’apprentissage profond pour ces applications. L’accent est aussi mis sur l’étude des différentes configurations d’acquisitions possibles et le débit de la méthode. Le dernier chapitre revient sur les principaux résultats élaborés au cours de cette thèse et ouvre différentes perspectives pour le phénotypage haut-débit en remplacement ou complément des mesures manuelles classiquement réalisées par les sélectionneurs et propose des pistes pour améliorer les méthodes développées
Genetic progress is one of the major leverage used to increase food production and satisfy the needs for the increasing human population under global change issues. Selecting or creating the optimal cultivar for a given location is quite challenging considering the very large spatial and temporal variability of the environmental conditions. Field phenotyping, i.e. the quantitative monitoring of crop state variables and canopy functioning, was recognized as the bottleneck to accelerate genetic progress and increase crop yield. This multidisciplinary study develops statistical and image processing methods to estimate the several structural traits of wheat to be applied to crop breeding. Further, this thesis was undertaken in the context of rapid hardware and software technological advancements illustrated by the increasing accessibility to UAV (Unmanned Aerial Vehicle) and UGV (Unmanned Ground Vehicle) platforms, the decreasing cost of processing units (GPUs, cloud computing) and the boom in the development of deep learning algorithms. This manuscript is divided into five chapters: The first chapter introduces the motivation behind the study as well as the current needs for high throughput phenotyping. A state of the art on phenotyping is also achieved by drawing attention to image processing methods and convolutional neural networks. The second chapter presents the development of methodologies for estimating the crop height. The feasibility of two main technologies and platforms were compared and proven: LiDAR mounted on a UGV and RGB (Red Green Blue) images acquired by a UAV. The next two chapters address the problem of estimating the density of wheat ears and stems from spatial high-resolution images. The results show the potential and limitations of deep learning for this application. Emphasis is also put on the study of the different possible acquisition configurations and the throughput of the method. The last chapter summarizes the pipelines developed and draws different perspectives of high throughput phenotyping to replace or supplement in-situ measurements as well as the improvement facilitated by the methods developed

Described is the development of a multispectral image labeling system with emphasis on Unmanned Ground Vehicles(UGVs). UGVs operating in unstructured environments face significant problems detecting viable paths when LIDAR is the sole source for perception. Promising advances in computer vision and machine learning has shown that multispectral imagery can be effective at detecting materials in unstructured environments [1][2][3][4][5][6]. This thesis seeks to extend previous work[6][7] by performing pixel level classification with multispectral features and texture. First the images are spatially registered to create a multispectral image cube. Visual, near infrared, shortwave infrared, and visible/near infrared polarimetric data are considered. The aligned images are then used to extract features which are fed to machine learning algorithms. The class list includes common materials present in rural and urban scenes such as vehicles, standing water, various forms of vegetation, and concrete. Experiments are conducted to explore the data requirement for a desired performance and the selection of a hyper-parameter for the textural features. A complete system is demonstrated, progressing from the data collection and labeling to the analysis of the classifier performance.
Master of Science